Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
Patch Release v4.53.2 source code.tar.gz | 2025-07-11 | 18.4 MB | |
Patch Release v4.53.2 source code.zip | 2025-07-11 | 23.2 MB | |
README.md | 2025-07-11 | 548 Bytes | |
Totals: 3 Items | 41.7 MB | 0 |
This patch contains the following bug fixes:
- Fix some bug for finetune and batch infer For GLM-4.1V (#39090)
- [bugfix] fix flash attention 2 unavailable error on Ascend NPU (#39166)
- Fix errors when use verl to train GLM4.1v model (#39199)
- [pagged-attention] fix off-by-1 error in pagged attention generation (#39258)
- [smollm3] add tokenizer mapping for
smollm3
(#39271) - [sliding window] revert and deprecate (#39301)
- fix Glm4v batch videos forward (#39172)
- Add a default value for
position_ids
in masking_utils (#39310)